Meta-Aggregating Networks for Class-Incremental Learning
share
Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase. The inherent problem in CIL is the stability-plasticity dilemma between the learning of old and new classes, i.e., high-plasticity models easily forget old classes but high-stability models are weak to learn new classes. We alleviate this issue by proposing a novel network architecture called Meta-Aggregating Networks (MANets) in which we explicitly build two residual blocks at each residual level (taking ResNet as the baseline architecture): a stable block and a plastic block. We aggregate the output feature maps from these two blocks and then feed the results to the next-level blocks. We meta-learn the aggregating weights in order to dynamically optimize and balance between two types of blocks, i.e., between stability and plasticity. We conduct extensive experiments on three CIL benchmarks: CIFAR-100, ImageNet-Subset, and ImageNet, and show that many existing CIL methods can be straightforwardly incorporated on the architecture of MANets to boost their performance.
READ FULL TEXT